To date, in matters of processing and managing network traffic, there is no single approach applicable to a wide pool of practical and applied tasks that would allow solving traffic management issues. Published works in this area are aimed at solving highly specialized problems: when applying complex solutions, these problems require the introduction of many additional parameters that increase computational complexity or solve only narrowly focused problems. This article provides a comparative analysis of classical network traffic models and reveals the possibility of practical application of such models in real-life problems. Classical traffic models are considered in detail, namely the Poisson model, heavy-tail traffic models, models based on Markov chains, traffic models based on the fractal theory and models based on stochastic time series. A mathematical description of each traffic model is also presented. Based on the results of the comparative analysis, the applicability of mathematical models to real projects was assessed. Based on it, two main problems were identified: first, the lack of consideration of the previous results of network traffic processing; secondly, the narrowly focused applicability of each of the models, given the rigid binding to subject areas, which allows solving only a narrow range of problems. The following indicators were taken as the criteria for evaluating network traffic models: the ability to scale the analyzed traffic, the ability to consider previous traffic data, computational complexity and the absence of some random features that could affect the operation of the model. A detailed study of the problem of traffic scaling revealed the main patterns, dependencies, dimensions of the traffic packet by the time it was processed.

No abstract

The current stage of development of the world community is characterized by an everincreasing role of the information sphere and is completely dependent on information resources and technologies, their quality and security. Computerization of all aspects of life has become the main reason that a significant part of the elements of social relations cannot be implemented without the use of new IT in various subject areas, and hence without the implementation of a reliable system of integrated security of the developed information automated systems. This article gives the concept of network traffic, considers the classification of network traffic, in which classification by port numbers, deep packet analysis, stochastic packet analysis, and the use of machine learning were identified. Methods for protecting information using trusted technologies were defined, where a general presentation of trust technologies was considered. The main conclusions are drawn on the prospects of using machine learning to classify network traffic in trusted technologies.

One of the most common methods for automatically determining the type of content in incoming traffic and limiting it is the system of black and white lists. Blacklists and whitelists are a set of “trusted” or “untrustworthy” rules for classifying data within information packets by which unwanted content is filtered. The object of the research is the existing traffic that will be divided into two groups in the form of "True-traffic" and "False-traffic". According to the compiled black and white lists, the number of hits of each traffic unit is determined and according to these data, an assessment of this approach to analysis is given. In accordance with the list of blocked signatures, the number of true blockings has high positive indicators and the number of false positives is close to zero with a VPN connection and starting a proxy server you can bypass content filtering, with transferring the resource to another URL blocking doesn’t occur, that was revealed on the cyberpolygon created to study the tasks of content filtering.